[HTML][HTML] Photonic neural networks based on integrated silicon microresonators

S Biasi, G Donati, A Lugnan, M Mancinelli… - Intelligent …, 2024 - spj.science.org
Recent progress in artificial intelligence (AI) has boosted the computational possibilities in
fields in which standard computers are not able to perform adequately. The AI paradigm is to …

Proximal alternating-direction-method-of-multipliers-incorporated nonnegative latent factor analysis

F Bi, X Luo, B Shen, H Dong… - IEEE/CAA Journal of …, 2023 - ieeexplore.ieee.org
High-dimensional and incomplete (HDI) data subject to the nonnegativity constraints are
commonly encountered in a big data-related application concerning the interactions among …

Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks

V Kunc, J Kléma - arXiv preprint arXiv:2402.09092, 2024 - arxiv.org
Neural networks have proven to be a highly effective tool for solving complex problems in
many areas of life. Recently, their importance and practical usability have further been …

Complex networks with complex weights

L Böttcher, MA Porter - Physical Review E, 2024 - APS
In many studies, it is common to use binary (ie, unweighted) edges to examine networks of
entities that are either adjacent or not adjacent. Researchers have generalized such binary …

A new cross ring neural network: Dynamic investigations and application to WBAN

D Jiang, ZT Njitacke, JDD Nkapkop… - IEEE Internet of …, 2022 - ieeexplore.ieee.org
Wireless body area network (WBAN) is a crucial tool in modern medical areas. This refers to
the intelligent interconnection of wireless sensor nodes installed outside or inside the …

A chaotic local search-based particle swarm optimizer for large-scale complex wind farm layout optimization

Z Lei, S Gao, Z Zhang, H Yang… - IEEE/CAA Journal of …, 2023 - ieeexplore.ieee.org
Wind energy has been widely applied in power generation to alleviate climate problems.
The wind turbine layout of a wind farm is a primary factor of impacting power conversion …

Jointly learning selection matrices for transmitters, receivers and fourier coefficients in multichannel imaging

H Wang, Y Zhou, E Pérez… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Strategic subsampling has become a focal point due to its effectiveness in compressing
data, particularly in the Full Matrix Capture (FMC) approach in ultrasonic imaging. This …

Fully complex-valued gated recurrent neural network for ultrasound imaging

Z Lei, S Gao, H Hasegawa, Z Zhang… - … on Neural Networks …, 2023 - ieeexplore.ieee.org
Ultrasound imaging is widely used in medical diagnosis. It has the advantages of being
performed in real time, cost-efficient, noninvasive, and nonionizing. The traditional delay …

A chaotic local search-based LSHADE with enhanced memory storage mechanism for wind farm layout optimization

Y Yu, T Zhang, Z Lei, Y Wang, H Yang, S Gao - Applied Soft Computing, 2023 - Elsevier
The search for clean energy alternatives to fossil fuels has been a major effort by
researchers all over the world. Wind energy is one of the most optimal choices because of its …

Theory and implementation of complex-valued neural networks

JA Barrachina, C Ren, G Vieillard, C Morisseau… - arXiv preprint arXiv …, 2023 - arxiv.org
This work explains in detail the theory behind Complex-Valued Neural Network (CVNN),
including Wirtinger calculus, complex backpropagation, and basic modules such as complex …